modularity

Tag

Cards List
#modularity

Modularity-Free Conflict-Averse Training for Generalized PINNs

arXiv cs.AI · yesterday Cached

This paper identifies a capacity-induced failure mode in physics-informed neural networks (PINNs) where overparameterized networks develop functional modularity that hinders convergence, and proposes Modular-Sparsity Synchronization (ModSync), a framework that penalizes task-exclusive connections to maintain cross-objective interaction and achieve state-of-the-art accuracy.

0 favorites 0 likes
#modularity

Biological evolution and information acquisition

Hacker News Top · 2026-06-11 Cached

This article draws parallels between biological evolution and technological evolution, explaining how modularity and sexual reproduction allow populations to increase the rate of information acquisition. Simulations demonstrate that mixing genetic material accelerates the spread of beneficial mutations, analogous to how technologies build on existing components.

0 favorites 0 likes
#modularity

LatentSkill: From In-Context Textual Skills to In-Weight Latent Skills for LLM Agents

Hugging Face Daily Papers · 2026-06-04 Cached

LatentSkill converts textual skills into LoRA adapters stored in weight space, reducing context overhead while maintaining modularity and composability for LLM agents, achieving significant improvements on ALFWorld and Search-QA benchmarks.

0 favorites 0 likes
#modularity

Learning to Construct Practical Agentic Systems

arXiv cs.LG · 2026-06-02 Cached

This paper proposes principled approaches for designing and optimizing practical agentic LLM systems, introducing a framework with pseudo-tools and fixed workflows to improve modularity, cost-efficiency, and accuracy across diverse tasks.

0 favorites 0 likes
#modularity

EMO: Pretraining mixture of experts for emergent modularity

Hugging Face Blog · 2026-05-08 Cached

Allen AI releases EMO, a mixture-of-experts model where modular structure emerges naturally from data, enabling use of just 12.5% of experts for a task while maintaining near full-model performance.

0 favorites 0 likes
← Back to home

Submit Feedback